Plugins

Custo de API por sessão e diário, orçamento com % de uso, saldo oficial, dashboard de histórico e sincronização de preços oficiais com um clique, incluindo tarifação de horário de pico/fora de pico.

Deep-read books and articles in five modes (quick, deep, knowledge map, Feynman, full book) with claim-evidence-data reports, Mermaid/XMind mindmaps, batch comparison, budget preflight, transparent background-job progress, and MD/HTML exports from URLs, files, or pasted text.

Registros persistentes de uso de tokens por sessão e um dashboard de configurações com detalhamento por provedor/modelo e um mapa de calor de atividade de 52 semanas.

Optimize a raw instruction into a professional prompt through the harness llm service — four-section (Role / Task / Context / Format) or a headerless plain-text style. Context-aware by default: the recent conversation is injected as background and may enrich the ## Context section. Long outputs resume from the truncation point with auto-expanded budgets; validated results are cached (identical requests cost zero model calls); a unified call budget bounds worst-case cost. Composer ✨ one-click optimize, undo, cancel and a token-cost hint; prompt_optimize tool (optimize + iterate), auto-optimize hook, auto-detected zh/en role document.

Um HUD de canto para o DeepSeek Harness que mostra, em um relance, a pressão de tokens da sua sessão, o custo por modelo e o uso diário/mensal, com orçamento e saldo editáveis que acompanham seus gastos por você. Um painel de tokens fixo no canto inferior direito: veja em tempo real a pressão da sessão e o gasto estimado por modelo. Orçamento e saldo podem ser editados com um clique, e o uso de cada dia e mês fica registrado.

Companheiro de sessão com quatro módulos: exportação inteligente de conversas (Markdown/PDF/JSON/imagem longa PNG, com redação de privacidade e ZIP em lote), resumos de transferência de contexto com salvamento/importação de modelos, otimização de custo de API (preços oficiais em tempo real, agendamento por horário de pico/fora de pico, orçamentos diários/mensais, roteamento de modelos) e busca global em conversas com localização no chat (Ctrl+F, CSS Custom Highlight API)

Rastreador de custo de tokens para o DeepSeek Harness — acompanha o uso, calcula custos e emite avisos de orçamento

China A-share financial data MCP server for the harness: 11 fin_data__* tools (quotes/K-lines/financials/calendar/special-data/announcements/EDB/reconcile/funds/indices) over THS free official REST (primary) + AKShare (fallback) + Wind (exclusive domains), with observable degradation, context-budget compression (result-side -72.2% measured), and an offline 10-year market-data lake; BYOK.

Cost tracking priced from an online catalogue (models.dev + OpenRouter, 8000+ models, each call priced at its own instant): a per-turn cost line, a Cost tab attributing spend to tool output / model output / system prompt / commands, budget, monthly forecast, ~166 live-rate currencies, and a bill_stats agent tool.

Gerenciamento de orçamento de tokens para a árvore de agentes

Personal bookkeeping for DeepSeek Harness: record expenses/income (single or batch), list, monthly/annual stats with trends, budgets with progress/over-limit alerts, soft-delete restore, CSV & self-contained HTML report. Zero deps, local JSON. 个人记账插件

Cost governance for DeepSeek Harness: aggregated token/cost metering per model, session and day, session/daily/monthly budget caps with threshold alerts (desktop notification + webhook) and alert/block/degrade over-limit policies, built-in carbon footprin

Long-term memory injected at session start: preferences/facts/summaries/knowledge in global and per-project scopes, budgeted recall via `agent/pre-step`, durable JSON store.

Enhanced auto-compaction defaults for DeepSeek Harness agent presets: apply tuned threshold/retention budgets and per-model policies with one command, idempotent with backups and rollback.

Deterministic aggregate media budgets and safe request projections for DeepSeek Harness (DSH)

DeepSeek Harness 插件 — 通过读取企划书 / 半成品软件 / 资料预估特定模型的 token 消耗量并实时按各家定价计费

Adaptive task and risk routing, loop budgets, and progressive tool-result pruning for DeepSeek Harness

Spend gate for DeepSeek Harness: refuses over-budget model calls on the llm/stream waterfall, before they are billed. Auto-downgrade past a soft limit.

Turn a paper into an academic talk for DeepSeek Harness (dsh) — 论文转 PPT / 组会汇报 / 会议报告 / 答辩 / 开题. Reads the real full text, budgets the slot per venue, and builds the deck around the figures with the speaker notes written as the script. Drives dsh-ai4schol

Configurable per-turn budgets for supported file mutations, limiting distinct files, mutation calls, and UTF-8 payload bytes before tool execution.

Local-life toolkit for DSH agents: budget planning, bill splitting, unit-price and discount math, common unit conversions (jin/li/chi, C/F, L/gallon), and trip checklists.

Two-phase session captioning: instant keyword titles while the conversation is busy, then cheapest-budget-model refinement plus a one-line summary once it goes idle.

Token usage and cost tracking with daily/session budget alerts and a usage_report tool.

Orçamentos com falha segura (fail-closed) por turno para etapas, chamadas de ferramenta e tokens de provedor no DeepSeek Harness